esphome-config-helper

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION] (LOW): The validate-config.sh script executes the esphome command as a subprocess. While it uses proper shell quoting for the filename argument to prevent basic command injection, the script's core purpose is to invoke a complex tool that processes user-provided YAML files.
  • [PROMPT_INJECTION] (LOW): The configuration templates use string interpolation (e.g., ${friendly_name}) within C++ lambda blocks. This creates an indirect prompt injection surface where unsanitized user input could lead to arbitrary C++ code being injected into the firmware during compilation. Evidence: Ingestion points: substitution variables in YAML templates; Boundary markers: C++ string literals; Capability inventory: C++ firmware compilation and execution; Sanitization: Absent in the provided templates.
  • [EXTERNAL_DOWNLOADS] (LOW): The display-node.yaml template references Google Fonts (gfonts://), which is a trusted external source. The skill also relies on the esphome Python package, a standard dependency for this use case.
  • [DATA_EXFILTRATION] (SAFE): The skill correctly implements the !secret directive for WiFi credentials, API encryption keys, and OTA passwords, ensuring that no sensitive data is hardcoded within the configuration files.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:58 PM